Recipes#

Recipes are relatively generic, built-in functionnalities for manipulating a compute graph in Aidge. Some are built with Aidge’s graph matching engine, do not hesitate to have a look at their source code to understand how they work and build similar functionnalities!

🚧 The list of recipes is still growing!

Adapt to backend #

Adapt a graph to the available kernels of a backend. The following transformations can be performed at the inputs and/or the outputs of operators: - Cast: change of data type; - Transpose: change of data format.

Python

aidge_core.adapt_to_backend(graph_view: aidge_core.aidge_core.GraphView) → None#

Adapt the graph to a specific backend.

Parameters:: graph_view (aidge_core.GraphView) – Graph view on which we want to apply the recipe

C++

void Aidge::adaptToBackend(std::shared_ptr<GraphView> graph)#

Adapt a graph to the available kernels of a backend.

Parameters:: graph – Graph to manipulate

Constant folding #

Fold constant operators (like ONNX Simplifier).

C++

void Aidge::constantFolding(std::shared_ptr<GraphView> graph)#

Convert Conv to MatMul #

Convert Conv operators to Unfold (im2col operation) + MatMul + Reshape.

C++

void Aidge::constantFolding(std::shared_ptr<GraphView> graph)

Input graph:

```mermaid %%{init: {‘flowchart’: { ‘curve’: ‘monotoneY’}, ‘fontFamily’: ‘Verdana’ } }%% flowchart TB

Producer_3(“conv2_wn(Producer#3)”):::producerCls Conv_1(“conv2n(Conv#1)”) Conv_0(“conv1n(Conv#0)”) Producer_2(“conv1_bn(Producer#2)”):::producerCls Producer_1(“conv1_wn(Producer#1)”):::producerCls Producer_4(“conv3_wn(Producer#4)”):::producerCls Conv_2(“conv3n(Conv#2)”) Producer_5(“conv3_bn(Producer#5)”):::producerCls Producer_0(“dataProvidern(Producer#0)”):::producerCls_rootCls Producer_3–>|”0 [7, 4, 3, 3]→1”|Conv_1 Conv_1-->|”0 [2, 7, 9, 20]→0”|Conv_2 Conv_0-->|”0 [2, 4, 11, 22]→0”|Conv_1 Producer_2-->|”0 [4]→2”|Conv_0 Producer_1-->|”0 [4, 3, 3, 3]→1”|Conv_0 Producer_4-->|”0 [10, 7, 1, 1]→1”|Conv_2 Producer_5-->|”0 [10]→2”|Conv_2 Producer_0-->|”0 [2, 3, 13, 24]→0”|Conv_0 input0((in#0)):::inputCls--->|”→2”|Conv_1 Conv_2--->|”0 [2, 10, 5, 10]→”|output0((out#0)):::outputCls classDef inputCls fill:#afa classDef outputCls fill:#ffa classDef externalCls fill:#ccc classDef producerCls fill:#ccf classDef genericCls fill:#f9f9ff,stroke-width:1px,stroke-dasharray: 5 5 classDef metaCls stroke-width:5px classDef rootCls stroke:#f00 classDef producerCls_rootCls stroke:#f00,fill:#ccf classDef genericCls_rootCls stroke:#f00,fill:#f9f9ff,stroke-width:1px,stroke-dasharray: 5 5 classDef metaCls_rootCls stroke:#f00,stroke-width:5px

```

Output graph:

```mermaid %%{init: {‘flowchart’: { ‘curve’: ‘monotoneY’}, ‘fontFamily’: ‘Verdana’ } }%% flowchart TB

Producer_0(“dataProvidern(Producer#0)”):::producerCls_rootCls MatMul_2(“conv3_matmuln(MatMul#2)”) Producer_7(“conv3_reshape_shape_prodn(Producer#7)”):::producerCls Reshape_2(“conv3_reshapen(Reshape#2)”) Add_1(“conv3_addn(Add#1)”) Producer_8(“conv3_b_reshape_0n(Producer#8)”):::producerCls Producer_1(“conv1_w_reshape_0n(Producer#1)”):::producerCls Unfold_2(“conv3_unfoldn(Unfold#2)”) Producer_3(“conv1_b_reshape_0n(Producer#3)”):::producerCls Unfold_0(“conv1_unfoldn(Unfold#0)”) MatMul_0(“conv1_matmuln(MatMul#0)”) Producer_2(“conv1_reshape_shape_prodn(Producer#2)”):::producerCls Reshape_0(“conv1_reshapen(Reshape#0)”) Add_0(“conv1_addn(Add#0)”) Unfold_1(“conv2_unfoldn(Unfold#1)”) MatMul_1(“conv2_matmuln(MatMul#1)”) Producer_5(“conv2_reshape_shape_prodn(Producer#5)”):::producerCls Reshape_1(“conv2_reshapen(Reshape#1)”) Producer_4(“conv2_w_reshape_0n(Producer#4)”):::producerCls Producer_6(“conv3_w_reshape_0n(Producer#6)”):::producerCls Producer_0–>|”0 [2, 3, 13, 24]→0”|Unfold_0 MatMul_2-->|”0 [2, 10, 50]→0”|Reshape_2 Producer_7-->|”0 [4]→1”|Reshape_2 Reshape_2-->|”0 [2, 10, 5, 10]→0”|Add_1 Producer_8-->|”0 [1, 10, 1, 1]→1”|Add_1 Producer_1-->|”0 [4, 27]→0”|MatMul_0 Unfold_2-->|”0 [2, 7, 50]→1”|MatMul_2 Producer_3-->|”0 [1, 4, 1, 1]→1”|Add_0 Unfold_0-->|”0 [2, 27, 242]→1”|MatMul_0 MatMul_0-->|”0 [2, 4, 242]→0”|Reshape_0 Producer_2-->|”0 [4]→1”|Reshape_0 Reshape_0-->|”0 [2, 4, 11, 22]→0”|Add_0 Add_0-->|”0 [2, 4, 11, 22]→0”|Unfold_1 Unfold_1-->|”0 [2, 36, 180]→1”|MatMul_1 MatMul_1-->|”0 [2, 7, 180]→0”|Reshape_1 Producer_5-->|”0 [4]→1”|Reshape_1 Reshape_1-->|”0 [2, 7, 9, 20]→0”|Unfold_2 Producer_4-->|”0 [7, 36]→0”|MatMul_1 Producer_6-->|”0 [10, 7]→0”|MatMul_2 Add_1--->|”0 [2, 10, 5, 10]→”|output0((out#0)):::outputCls classDef inputCls fill:#afa classDef outputCls fill:#ffa classDef externalCls fill:#ccc classDef producerCls fill:#ccf classDef genericCls fill:#f9f9ff,stroke-width:1px,stroke-dasharray: 5 5 classDef metaCls stroke-width:5px classDef rootCls stroke:#f00 classDef producerCls_rootCls stroke:#f00,fill:#ccf classDef genericCls_rootCls stroke:#f00,fill:#f9f9ff,stroke-width:1px,stroke-dasharray: 5 5 classDef metaCls_rootCls stroke:#f00,stroke-width:5px ```

Expand meta operators #

Expand meta operators, replacing them with their inner graph (flatten the graph).

Python

aidge_core.expand_metaops(graph_view: aidge_core.aidge_core.GraphView, recursive: bool = False) → None#

Flatten the graph by replacing the meta operators by their micro graph.

Parameters:

graph_view (aidge_core.GraphView) – Graph view on which we want to apply the recipe
recursive (bool) – If true, recursively replace meta operators until there is no more meta operator in the graph.

C++

void Aidge::expandMetaOps(std::shared_ptr<GraphView> graph, bool recursive = false)#

Flatten the graph by replacing the meta operators by their micro graph.

Parameters:: recursive – If true, recursively replace meta operators until there is no more meta operator in the graph.

Explicit Cast Move #

Insert Cast and Move operators where needed (thus removing all implicit data type conversion and backend change data movement).

C++

void Aidge::explicitCastMove(std::shared_ptr<GraphView> graphView)#: Add Cast and Move operators where needed to ensure no conversion needs to be done at the Operator level.

Explicit Transpose #

Insert Transpose operators where needed to ensure no transposition needs to be done at the Operator level (thus removing all implicit data format conversion).

C++

void Aidge::explicitTranspose(std::shared_ptr<GraphView> graphView)#: Add Transpose operators where needed to ensure no transposition needs to be done at the Operator level.

Fuse BatchNorm #

Fuse batch normalization with the preceding Conv or FC operator, if possible.

Python

aidge_core.fuse_batchnorm(graph_view: aidge_core.aidge_core.GraphView) → None#

Recipe to remove a flatten operator.

Parameters:: graph_view (aidge_core.GraphView) – Graph view on which we want to apply the recipe

C++

void Aidge::fuseBatchNorm(std::shared_ptr<GraphView> graphView)#

Fuse :cpp:function:Aidge::BatchNorm with :cpp:function:Aidge::Conv or :cpp:function:Aidge::FC Nodes. Ref: https://nenadmarkus.com/p/fusing-batchnorm-and-conv/.

Parameters:: graphView – Graph view to use graph matching on, in order to apply transformations.

Fuse MatMul and Add to FC #

Fuse MatMul optionnally followed by Add operator into a FC operator.

Python

aidge_core.matmul_to_fc(graph_view: aidge_core.aidge_core.GraphView) → None#

Recipe to Fuse MatMul and Add operators into an aidge_core.FC operator.

Parameters:: graph_view (aidge_core.GraphView) – Graph view on which we want to apply the recipe

C++

Warning

doxygenfunction: Cannot find function “Aidge::fuseMulAdd” in doxygen xml output for project “aidge” from directory: xml/

Fuse to meta operator #

Fuse each sub-graph matching a query in a Meta Operator.

Python

aidge_core.fuse_to_metaops(*args, **kwargs)#

Overloaded function.

fuse_to_metaops(gm: aidge_core.aidge_core.SinglePassGraphMatching, query: str, type: str = ‘’) -> int

Fuse each sub-graph matching a query in a Meta Operator.

param gm:

SinglePassGraphMatching containing the graph to manipulate

type gm:

aidge_core.SinglePassGraphMatching

param query:

Sub-graph matching query

type query:

str

param type:

Type name of the resulting meta operators

type type:

str, optional

return:

Number of sub-graph actually fused in a Meta Operator.

rtype:

int
fuse_to_metaops(graph_view: aidge_core.aidge_core.GraphView, query: str, type: str = ‘’) -> int

Fuse each sub-graph matching a query in a Meta Operator.

param graph_view:

Graph view on which we want to apply the recipe

type graph_view:

aidge_core.GraphView

param query:

Sub-graph matching query

type query:

str

param type:

Type name of the resulting meta operators

type type:

str, optional

return:

Number of sub-graph actually fused in a Meta Operator.

rtype:

int

C++

Warning

doxygenfunction: Unable to resolve function “Aidge::fuseToMetaOps” with arguments None in doxygen xml output for project “aidge” from directory: xml/. Potential matches:

- size_t fuseToMetaOps(SinglePassGraphMatching &gm, const std::string &query, const std::string &type = "")
- size_t fuseToMetaOps(std::shared_ptr<GraphView> graph, const std::string &query, const std::string &type = "")

MatMul tiling #

Tile any MatMul operator to several fixed size matrix multiplications. For instance, for a MatMul of size 80x80 and a tiling of 16x16, this will tile the MatMul operator to 25 (5 by 5) MatMul operators of size 16x16, with Slice operators inserted at the inputs and Concat operators inserted at the outputs.

This is especially useful when matrix multiplication must be mapped to fixed maximum size hardware TPU (Tensor Processing Unit) or MMA (Matrix Multiplication Accelerator). This recipe can be combined with the convToMatMul recipe in order to convert convolutions to matrix multiplication beforehand, and constantFolding recipe to fold sliced constant tensors.

C++

void Aidge::matMulTiling(NodePtr matMul, const std::vector<DimSize_t> &maxDims)#

Tile any :cpp:function:Aidge::MatMul operator to several fixed size matrix multiplications. For instance, for a MatMul of size 80x80 and a tiling of 16x16, this will tile the MatMul operator to 25 (5 by 5) MatMul operators of size 16x16, with Slice operators inserted at the inputs and Concat operators inserted at the outputs.

This is especially useful when matrix multiplication must be mapped to fixed maximum size hardware TPU (Tensor Processing Unit) or MMA (Matrix Multiplication Accelerator). This recipe can be combined with the :cpp:function:Aidge::convToMatMul recipe in order to convert convolutions to matrix multiplication beforehand, and :cpp:function:Aidge::constantFolding recipe to fold sliced constant tensors.

Parameters:

matMul – MatMul operator to be tiled.
maxDims – Maximum output dimensions of the tiled MatMul operators.

Initial graph:

```mermaid %%{init: {‘flowchart’: { ‘curve’: ‘monotoneY’}, ‘fontFamily’: ‘Verdana’ } }%% flowchart TB

MatMul_0(“matmul1 (MatMul#0)”):::rootCls Producer_1(“w1 (Producer#1)”):::producerCls Producer_0(“dataProvider (Producer#0)”):::producerCls MatMul_0—>|”0 [2, 3, 80, 80]→”|output0((out#0)):::outputCls Producer_1-->|”0 [2, 3, 80, 80]→1”|MatMul_0 Producer_0-->|”0 [2, 3, 80, 80]→0”|MatMul_0 classDef inputCls fill:#afa classDef outputCls fill:#ffa classDef externalCls fill:#ccc classDef producerCls fill:#ccf classDef genericCls fill:#f9f9ff,stroke-width:1px,stroke-dasharray: 5 5 classDef metaCls stroke-width:5px classDef rootCls stroke:#f00 classDef producerCls_rootCls stroke:#f00,fill:#ccf classDef genericCls_rootCls stroke:#f00,fill:#f9f9ff,stroke-width:1px,stroke-dasharray: 5 5 classDef metaCls_rootCls stroke:#f00,stroke-width:5px ```

Graph generated by a single step of the matMulTiling recipe (after the very first matrix multiplication split):

```mermaid %%{init: {‘flowchart’: { ‘curve’: ‘monotoneY’}, ‘fontFamily’: ‘Verdana’ } }%% flowchart TB

Producer_7(Producer#7):::producerCls MatMul_1(MatMul#1) Concat_0(Concat#0) Producer_1(Producer#1):::producerCls Producer_2(Producer#2):::producerCls Producer_3(Producer#3):::producerCls Producer_4(Producer#4):::producerCls Producer_5(Producer#5):::producerCls Producer_6(Producer#6):::producerCls Identity_0(Identity#0):::rootCls Slice_0(Slice#0) Producer_0(Producer#0):::producerCls MatMul_0(MatMul#0) Identity_1(Identity#1) Slice_1(Slice#1) Producer_7–>|”0 [2]→4”|Slice_1 MatMul_1-->|”0 [2, 3, 64, 80]→1”|Concat_0 Producer_1-->|”0 [2]→2”|Slice_0 Producer_2-->|”0 [2]→3”|Slice_0 Producer_3-->|”0 [2]→4”|Slice_0 Producer_4-->|”0 [2]→1”|Slice_1 Producer_5-->|”0 [2]→2”|Slice_1 Producer_6-->|”0 [2]→3”|Slice_1 Identity_0-->|”0 [2, 3, 80, 80]→0”|Slice_0 Identity_0-->|”0 [2, 3, 80, 80]→0”|Slice_1 Slice_0-->|”0 [2, 3, 16, 80]→0”|MatMul_0 Producer_0-->|”0 [2]→1”|Slice_0 MatMul_0-->|”0 [2, 3, 16, 80]→0”|Concat_0 Identity_1-->|”0 [2, 3, 80, 80]→1”|MatMul_1 Identity_1-->|”0 [2, 3, 80, 80]→1”|MatMul_0 Slice_1-->|”0 [2, 3, 64, 80]→0”|MatMul_1 input0((in#0)):::inputCls--->|”→0[2, 3, 80, 80]”|Identity_0 input1((in#1)):::inputCls--->|”→0[2, 3, 80, 80]”|Identity_1 Concat_0--->|”0 [2, 3, 80, 80]→”|output0((out#0)):::outputCls classDef inputCls fill:#afa classDef outputCls fill:#ffa classDef externalCls fill:#ccc classDef producerCls fill:#ccf classDef genericCls fill:#f9f9ff,stroke-width:1px,stroke-dasharray: 5 5 classDef metaCls stroke-width:5px classDef rootCls stroke:#f00 classDef producerCls_rootCls stroke:#f00,fill:#ccf classDef genericCls_rootCls stroke:#f00,fill:#f9f9ff,stroke-width:1px,stroke-dasharray: 5 5 classDef metaCls_rootCls stroke:#f00,stroke-width:5px ```

Remove Dropout #

Remove Dropout operators.

C++

size_t Aidge::removeDropout(std::shared_ptr<GraphView> graphView)#

Remove Dropout Node.

Parameters:: graphView – Graph view to use graph matching on, in order to apply transfomrations.
Returns:: size_t Number of identity nodes removed

Remove Flatten #

Remove Flatten operators.

Python

aidge_core.remove_flatten(graph_view: aidge_core.aidge_core.GraphView) → None#

Recipe to remove a Flatten operator if it is followed by a FC or a MatMul. The recipe can remove multiple Flatten operator if they are one after the other.

Parameters:: graph_view (aidge_core.GraphView) – Graph view on which we want to apply the recipe.

C++

void Aidge::removeFlatten(std::shared_ptr<GraphView> graphView)#

Remove Flatten before :cpp:function:Aidge::FC Node.

Parameters:: graphView – Graph view to use graph matching on, in order to apply transformations.

Recipes#

This Page